{
  "slug": "llama-cpp",
  "category": "ai-assistants",
  "name": "llama.cpp",
  "description": "Open-source C/C++ library and command-line tools for running large language model inference locally on CPUs and GPUs, including a built-in web server and chat interface.",
  "website": "https://github.com/ggml-org/llama.cpp",
  "source": "https://github.com/ggml-org/llama.cpp",
  "license": "MIT",
  "platforms": [
    "windows",
    "macos",
    "linux"
  ],
  "jurisdiction": null,
  "pick": false,
  "pick_reason": null,
  "disclosure": null,
  "grade": "B",
  "score": 89,
  "coverage": 100,
  "summary": "llama.cpp scores 89 out of 100 (grade B) on the AI assistants criteria. It meets 7 of 8 criteria: open source, no trackers or telemetry, no ads or data sales, no training on your data, runs locally, limited chat retention and no account needed. It does not meet independent audit.",
  "url": "https://privacyratings.com/ai-assistants/llama-cpp/",
  "markdown": "https://privacyratings.com/ai-assistants/llama-cpp/index.md",
  "answers": {
    "open_source": {
      "title": "Open source",
      "weight": 3,
      "answer": "yes",
      "evidence": "https://github.com/ggml-org/llama.cpp/blob/master/LICENSE",
      "note": "MIT."
    },
    "no_trackers": {
      "title": "No trackers or telemetry",
      "weight": 3,
      "answer": "yes",
      "evidence": "https://github.com/ggml-org/llama.cpp",
      "note": "No telemetry or analytics in the source code."
    },
    "no_ads": {
      "title": "No ads or data sales",
      "weight": 2,
      "answer": "yes",
      "evidence": "https://github.com/ggml-org/llama.cpp",
      "note": "Free and open source, with no ads."
    },
    "independent_audit": {
      "title": "Independent audit",
      "weight": 2,
      "answer": "no",
      "evidence": null,
      "note": "No independent audit is published."
    },
    "transparency_report": {
      "title": "Transparency report",
      "weight": 2,
      "answer": "n/a",
      "evidence": null,
      "note": "Only applies to hosted services with a website to test."
    },
    "user_notice": {
      "title": "Tells users about requests",
      "weight": 1,
      "answer": "n/a",
      "evidence": null,
      "note": "Only applies to hosted services with a website to test."
    },
    "tls": {
      "title": "TLS configuration",
      "weight": 2,
      "answer": "n/a",
      "evidence": null,
      "note": "Only applies to hosted services with a website to test."
    },
    "security_headers": {
      "title": "Security headers",
      "weight": 1,
      "answer": "n/a",
      "evidence": null,
      "note": "Only applies to hosted services with a website to test."
    },
    "web_standards": {
      "title": "Modern web standards",
      "weight": 1,
      "answer": "n/a",
      "evidence": null,
      "note": "Only applies to hosted services with a website to test."
    },
    "no_training": {
      "title": "No training on your data",
      "weight": 3,
      "answer": "yes",
      "evidence": "https://github.com/ggml-org/llama.cpp",
      "note": "Runs entirely on the user's hardware, so prompts are never sent anywhere."
    },
    "runs_locally": {
      "title": "Runs locally",
      "weight": 2,
      "answer": "yes",
      "evidence": "https://github.com/ggml-org/llama.cpp",
      "note": "Runs models locally on the user's own hardware."
    },
    "chat_retention": {
      "title": "Limited chat retention",
      "weight": 2,
      "answer": "yes",
      "evidence": "https://github.com/ggml-org/llama.cpp",
      "note": "No server copy exists; everything stays on the user's machine."
    },
    "no_account_needed": {
      "title": "No account needed",
      "weight": 1,
      "answer": "yes",
      "evidence": "https://github.com/ggml-org/llama.cpp",
      "note": "No account is needed."
    }
  },
  "tests": {
    "ssllabs": null,
    "observatory": null,
    "internetnl_web": null,
    "internetnl_mail": null,
    "trackers": null,
    "tested_at": "2026-10-01T06:38:49.803Z"
  },
  "last_modified": "2026-10-01T06:56:31Z"
}